Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    discussions about research findings and scientific results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Punctuation followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    sentence starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bezeichneter
    -0.49
    цездатний
    -0.46
    IVEREF
    -0.43
    -0.36
    UnusedPrivate
    -0.36
     TextAppearance
    -0.35
    )|\
    -0.35
    شهاد
    -0.35
     %{
    -0.34
    !»
    -0.34
    POSITIVE LOGITS
     now
    0.59
     теперь
    0.56
    Now
    0.55
    Теперь
    0.54
    Maintenant
    0.54
     but
    0.53
    󠁣
    0.51
     maintenant
    0.51
     Now
    0.50
    CloseOperation
    0.49
    Act Density 0.436%

    No Known Activations